Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 32 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0005

Data Index: 74818 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0226. Min Act: -0.0005

Data Index: 505638 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0005

Data Index: 533934 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0005

Data Index: 957297 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0209. Min Act: -0.0005

Data Index: 812132 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1170852 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0005

Data Index: 333594 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1022553 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0207. Min Act: -0.0005

Data Index: 716616 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0204. Min Act: -0.0005

Data Index: 1301678 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0205. Min Act: -0.0005

Data Index: 292824 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0201. Min Act: -0.0005

Data Index: 893431 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1169213 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1153653 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1156641 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0200. Min Act: -0.0005

Data Index: 660162 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1057334 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0206. Min Act: -0.0005

Data Index: 850188 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0197. Min Act: -0.0005

Data Index: 585916 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0191. Min Act: -0.0005

Data Index: 835407 (C4 (Web Text))

Max Activating Token Index: 497